What languages are supported for transcription?

Parakeel models support 50+ languages including English, Portuguese, Spanish, French, German, Mandarin, Japanese, and many more. Specify the language for best results.

Can I clone a specific voice?

Yes! Use the `clone_voice` tool with a reference audio sample (a few seconds is enough) and the text you want the cloned voice to speak.

What is speaker diarization?

Speaker diarization identifies 'who spoke when' in an audio recording. It segments the audio by speaker and returns timestamps for each speaker's turns.

What audio formats are supported?

The API supports WAV, MP3, FLAC, OGG, and most common audio formats. For best transcription accuracy, use high-quality WAV or FLAC files at 16kHz or higher sample rate.

NVIDIA Audio MCP Server

Name: NVIDIA Audio
Availability: InStock
Author: Vinkius

nvidia.com

Built by Vinkius GDPR ToolsFree

Transcribe speech, generate voices, translate audio, and clone voices via NVIDIA Audio APIs.

Vinkius AI Gateway supports streamable HTTP and SSE.

Works with every AI agent you already use

…and any MCP-compatible client

NVIDIA MCP Server: see your AI Agent in action

AI Agent→Vinkius→NVIDIA Audio

You

Vinkius AI Gateway

GDPR·High Security·Kill Switch·Ultra-Low Latency·Plug and Play

Built-in capabilities (10)

audio_translation

Provide target language. Translate spoken audio to another language

cancel_noise

Remove background noise from audio

classify_audio

) with confidence scores. Classify the type of sound in an audio file

clone_voice

Clone a voice from a reference audio and generate speech

list_audio_models

List available audio models on NVIDIA API Catalog

punctuate_text

Add punctuation and capitalization to raw text

speaker_diarization

Identify different speakers in an audio file

speech_to_text

Supports multiple languages. Provide a public audio URL (MP3, WAV, etc). Transcribe speech from audio to text (Whisper-style)

summarize_audio

Summarize an audio transcript

text_to_speech

Optional voice parameter for different voices. Convert text to natural-sounding speech

What this connector unlocks

Connect NVIDIA Audio to any AI agent and unlock professional-grade audio processing — transcribe speech to text, generate natural voices, translate audio across languages, perform speaker diarization, and clone voices through natural conversation.

What you can do

Speech-to-Text — Transcribe audio files with high accuracy using Parakeel models
Text-to-Speech — Convert text to natural-sounding speech
Audio Translation — Translate spoken audio directly to another language
Speaker Diarization — Identify and separate different speakers in audio
Voice Cloning — Clone a voice from a sample and generate new speech
Noise Cancellation — Remove background noise from recordings
Audio Classification — Classify audio as speech, music, noise, etc.
Punctuation Restoration — Add punctuation to raw speech-to-text output

How it works

1. Subscribe to this server 2. Enter your NVIDIA API Key (from build.nvidia.com) 3. Start processing audio from Claude, Cursor, or any MCP-compatible client

Who is this for?

Transcription Services — Automate meeting notes, podcast transcripts, and subtitles
Content Creators — Generate voiceovers and clone voices for multilingual content
Customer Support — Analyze call recordings with diarization and sentiment analysis

Frequently asked questions

Give your AI agents the power of NVIDIA

Access NVIDIA and 2,000+ MCP servers — ready for your agents to use, right now. No glue code. No custom integrations. Just plug Vinkius AI Gateway and let your agents work.

DETAILS

CategoryIndustry Titans